Presentation is loading. Please wait.

Presentation is loading. Please wait.

Emergent Design Martin HembergImperial College2004Emergent Design.

Similar presentations


Presentation on theme: "Emergent Design Martin HembergImperial College2004Emergent Design."— Presentation transcript:

1 Emergent Design Martin HembergImperial College2004Emergent Design

2 Who's that guy and what's he doing up there? ● Martin Hemberg ● Developed Genr8 with the Emergent Design Group (EDG) ● Work at Emergent Design + Technologies (EmTech) Architectural Association (AA) Martin HembergImperial College2004Emergent Design

3 Agenda ● Motivation ● Evolutionary Computation (EC) ● Artificial Life (Alife) – EC and Alife combine well for design tasks ● Example applications Design Evolutionary Computation Artificial Life Emergent Design Martin HembergImperial College2004Emergent Design

4 Motivation, Architecture ● Break new grounds in architecture – ED uses a different logic ● Natural form has aesthetic and functional values ● Hard to obtain using ordinary methods Martin HembergImperial College2004Emergent Design

5 Motivation, Computer Science ● Application of EC – Exploration, not optimisation – Fitness evaluation ● Use computers creatively – Beyond CAD-tools – Requires new algorithms Martin HembergImperial College2004Emergent Design

6 Evolutionary Computation ● Optimisation method – Randomized ● Inspired by natural evolution – Population adaption generation by generation ● Comes in many flavours: GA, GP, ES, GE, etc Martin HembergImperial College2004Emergent Design

7 Neo Darwinian Evolution ● Survival of the fittest ● Selection on phenotype – Through environment ● Genotypic inheritance ● Reproduction ● Blind variation Martin HembergImperial College2004Emergent Design

8 Artificial Evolution Pseudocode for an EA: generation = 0; initialize population; while generation child; mutate child; insert child into next generation’s population; endfor; generation++; update current population endwhile; Iterate by generation Fitness biased selection Inheritance Variation Martin HembergImperial College2004Emergent Design

9 Selection ● Selection ensures that fitter individuals have a higher probability of being selected for the next generation – Tournament – Proportional Martin HembergImperial College2004Emergent Design

10 Fitness ● A leap from natural evolution ● A quantified numerical value is assigned to each member ● Try each member on the problem and rank them or quantify their performance Martin HembergImperial College2004Emergent Design

11 Fitness Evaluation ● How to assign fitness according to aesthetic criteria? – EA are good at finding optimal solutions – Need to figure out what to optimize ● Open problem Martin HembergImperial College2004Emergent Design

12 Fitness Evaluation, strategies ● Rule based – Hard to define and encode rules ● Learn user preference with neural network – Too many parameters, fails in practice ● User acts as fitness function – Human fatigue, short runs ● Co-evolve critics Martin HembergImperial College2004Emergent Design

13 Fitness Evaluation, my view ● Put the user in the loop ● Create tools with the designer in mind – Make them open-ended – Can't predict user's need and context ● Parameterized fitness function – User has high level control of evaluation – Fitness emerges as a combination of factors Martin HembergImperial College2004Emergent Design

14 What is Artificial Life How does life arise from the non-living? What are the potentials and limits of living systems? How is life related to mind, machines, and culture? Martin HembergImperial College2004Emergent Design

15 Two definitions of emergence ● The whole is greater than the sum of the parts ● Emergence is the phenomenon wherein complex, interesting high-level function is produced as a result of combining simple low-level mechanisms in simple ways. ● Examples include brain, society Martin HembergImperial College2004Emergent Design

16 Alife and EC for Design ● Evolutionary computation – Creative and generative qualities – Discovery and adaptation more than optimization ● ALife – Agents interacting with environment can model elements of design and conditions of the problem – Emergent properties in outcome from bottom-up approach The ‘fit’ is powerful and good, but not perfect Martin HembergImperial College2004Emergent Design

17 Surface Component System ● Simple growth model – Select tiles from a predefined set – Rules for which tiles are allowed ● Incorporates structural analysis in the EA Martin HembergImperial College2004Emergent Design

18 Using the tool ● Implemented as a MEL script ● FEA in Ansys Martin HembergImperial College2004Emergent Design

19 Geometric Fitness criteria ● Fast and easy to evaluate and understand – Number of support points – Support point distance – Height – Holes Martin HembergImperial College2004Emergent Design

20 Structural Fitness criteria ● FEA is computationally costly – Don't evaluate each generation Martin HembergImperial College2004Emergent Design

21 Genr8 – A Design Tool for Surface Generation ● Combines EC and an organic growth model ● Surface are grown in a reactive simulated physical environment Martin HembergImperial College2004Emergent Design

22 Lindenmayer Systems ● Organic growth model ● Widely applied to model plant growth in computer graphics ● L-systems are important in formal language theory Martin HembergImperial College2004Emergent Design

23 Rewriting systems ● A set of production rules are repeatedly applied to a seed ● Rules are expressed as a grammar Seed:a Rule:a->ab b->ba Martin HembergImperial College2004Emergent Design

24 Turtle Graphics ● Turtle graphics is a way to visualize the grammar – Rules are interpreted as instructions for moving and drawing in 3D space Seed:a Rule:a->a+a--a+a Angle:60 Martin HembergImperial College2004Emergent Design

25 Plant Models ● Operators “[“ (push state on stack) and “]” (pop state from stack) allows branching – Time delay – Stochasticity – Environmen (tropism) Seed:a Rule:a->a[+a]a Angle:45 Martin HembergImperial College2004Emergent Design

26 Map L-Systems a -> d[~a]b a b d a b -> b b b c -> b[-~a]b ba b c d -> c dc seed d c b a c b b bb a a d bb b b d c a b b b b b b b a c d b b b b b b b a b b b d c b b b b b b b Bb b c Martin HembergImperial College2004Emergent Design

27 HEMLS ● 3D ● Scaling ● More complex productions – Context sensitivity – Time variation – Stochastic Martin HembergImperial College2004Emergent Design

28 Environment ● Forces – Attractors – Repellors – Gravity ● Boundary Martin HembergImperial College2004Emergent Design

29 Evolution ● Search the universe of possible surfaces – Find a grammar corresponding to the surface that the designer has in mind – Explore the universe to find interesting forms Martin HembergImperial College2004Emergent Design

30 Grammatical Evolution ● Automatic generation of grammars – Very hard to construct by hand ● Many constraints -> problematic for GP ● Grammatical Evolution allows any language – Use Backus-Naur Form (BNF) to map linear genome into a grammar – Genetic operations are separated from language Martin HembergImperial College2004Emergent Design

31 Mappings ● Genr8 contains several mappings – Increases the complexity ● Individuals represented by linear genome ● Selection on the phenotype that is expressed through an environment Martin HembergImperial College2004Emergent Design

32 Design Evaluation and Fitness ● Fitness function with multiple parameters – Size – Smoothness – Soft boundary – Subdivisions – Symmetry – Undulation Martin HembergImperial College2004Emergent Design

33 Fitness Criteria ● User determines target values and weight for the criteria – Multiparameter optimization – Trade-off between criteria – Population gives a family of solutions Martin HembergImperial College2004Emergent Design

34 Interruption, Intervention and Resumption (IIR) ● Traditionally, EA are monolithic ● User can guide the evolution by interacting and interfering – Allows for greater control – The tool cooperates with the user Martin HembergImperial College2004Emergent Design

35 Using Genr8 ● Set up environment ● Define fitness criteria and other parameters ● Run a few generations ● Analyze the results, adjust parameters and environment Martin HembergImperial College2004Emergent Design

36 More on Emergent Design ● Genr8 website http://www.ai.mit.edu/projects/emergentDesign/genr8/ http://www.ai.mit.edu/projects/emergentDesign/genr8/ ● EDG website http://web.mit.edu/arch/edg/ http://web.mit.edu/arch/edg/ ● EmTech website ● http://www.aaschool.ac.uk/et Martin HembergImperial College2004Emergent Design


Download ppt "Emergent Design Martin HembergImperial College2004Emergent Design."

Similar presentations


Ads by Google